Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.8057. Min Act: -0.0000

Data Index: 760929 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.7220. Min Act: -0.0000

Data Index: 430836 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.7678. Min Act: -0.0000

Data Index: 853889 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.7606. Min Act: -0.0000

Data Index: 644807 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5521. Min Act: -0.0000

Data Index: 706510 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5482. Min Act: -0.0000

Data Index: 906043 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5942. Min Act: -0.0000

Data Index: 448585 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1248750 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5825. Min Act: -0.0000

Data Index: 251950 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1243651 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5384. Min Act: -0.0000

Data Index: 737545 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5395. Min Act: -0.0000

Data Index: 696290 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1108835 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1296621 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4506. Min Act: -0.0000

Data Index: 164638 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4981. Min Act: -0.0000

Data Index: 956561 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4853. Min Act: -0.0000

Data Index: 749484 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3634. Min Act: -0.0000

Data Index: 571205 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1277293 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1160075 (C4 (Web Text))

Max Activating Token Index: 1008